Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| rossbus — buses across Russia xpressmike/rossbus-mcp Buses across Russia: routes, prices, departure times, stations, transfers, price-per-km index | |
| XRPName xrpdomains/xrpname-mcp-server XRPL domains for AI agents — availability, pricing, profiles, portfolio, and register links. | |
| XRPL-Utilities xrpl-utilities/xrpl-utilities-mcp XRPL data tools for AI agents: wallet classifier, signals, RWA tracker, ETF flows. Pay via x402. | |
| Playwright E2E MCP xsignon-secure/e2e Diagnose and fix Playwright tests (TS, pytest): CI reports, traces, verified fixes, flaky verdicts. | |
| MCP Document Reader xt765/mcp_documents_reader An MCP enabled multi-format document reader supporting DOCX, PDF, TXT, and Excel files | |
| io.github.xt765/mcp-document-converter xt765/mcp-document-converter Convert PDF, DOCX, HTML, Markdown, and Text for AI assistant context injection. | |
| XTELL Serial xtell-cn/xtell-serial Serial terminal with a GUI that AI assistants drive over MCP: read device logs, send commands. | |
| io.github.xtrustinfo/company-lookup xtrustinfo/mcp-server-xtrust Ukrainian business directory: companies, contacts and registry details (xtrust.info). | |
| io.github.xu-c0/cybersec-mcp xu-c0/cybersec-mcp Cybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT. | |
| io.github.xultrax-web/agent-memory-mcp xultrax-web/agent-memory-mcp Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database. | |
| DogPolicies xultrax-web/dogpolicies-mcp Verified dog rules for California and Nevada travel: parks, beaches, hotels, fees, sourced and dated | |
| Ask Xverum xverum-llc/xverum-mcp Find and enrich people from 750M professional profiles, with Next Move Signal job-change scores. | |
| PDF Reader xvvln/pdf-reader-mcp MCP server for extracting text, images, tables, links, annotations, and metadata from PDF files. | |
| io.github.XXO47OXX/spa-reader-mcp xxo47oxx/spa-reader-mcp MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content | |
| io.github.xxxoooxoxo/wiff xxxoooxoxo/wiff Deterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi. | |
| brain-core xy-claude/brain-core Memory for a Claude Code agent that survives the session: five tools, a markdown vault, all local. | |
| ocular xyun1996/ocular Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts. | |
| tc39-mcp xyzzylabs/tc39-mcp Independent MCP server for the TC39 specs (ECMA-262 + ECMA-402): clauses, search, diffs, history. | |
| wasm-mcp xyzzylabs/wasm-mcp Read-only MCP server for the WebAssembly spec: instructions, types, sections, search, proposals. | |
| Xzar xzar-si/xzar-mcp Crash-test your AI agent on real professional decisions, graded against what actually happened. | |
| Mixer AI y110692/mixerai-mcp Create and edit images, video, music and voice with 100+ AI models and Canvas. | |
| com.balmasai/balmas-mcp yaakovtzedek/balmas-mcp Agents read cleaned copies of your files: PII replaced with local consistent tokens. Read-only. | |
| LyricPatch yaboijbigs/lyricpatch-agent Signup-free lyric editing: upload authorized audio, change words, preview, and download. | |
| WHOOP Health Signals yadheedhya06/mcp-server-whoop Local-first, read-only WHOOP MCP server for recovery, sleep, strain, workouts, and body signals | |
| dev.yafl/mcp yafldev/mcp Agent-first E2EE file transfer over MCP: move files between machines in one tool call, gone in 24h. | |
| ReClip yagyaanshk/reclip Inspect and download authorized media or precise clips locally with yt-dlp. | |
| AimYear yahhi/aimyear-mcp Accountability partner in your agent: one yearly aim, one main step a day, a timer your agent runs. | |
| FrankenSurf yail259/frankensurf Read any web page and search the web: 28 tools, cheapest first, every page checked. | |
| io.github.yakub268/kalshi yakub268/kalshi-mcp Search, analyze, and trade Kalshi prediction markets through Claude Desktop | |
| io.github.YakupEmreYerli/mcp-firefly-iii yakupemreyerli/mcp-firefly-iii Security-first, self-hosted MCP server for Firefly III — 152 operations behind 5 scoped tools. | |
| Education Scope MCP yama-tana/education_scope_mcp Classify Japanese curriculum scope, audit grade limits, and search normalized MEXT data. | |
| Repomix yamadashy/repomix Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search | |
| io.github.yamaru-eu/hardware-probe yamaru-eu/hardware-probe Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization. | |
| PaletteGet yang7206/paletteget-mcp Curated app, web and mini program color palettes with WCAG contrast and CSS variables. | |
| Memory Bridge (忆桥) yanglinfeng/memory-bridge Evidence-cited knowledge base for internal documents: audit trail, versioning, namespace isolation. | |
| Overleaf yangzichao/mcp-server-overleaf Overleaf MCP server for Claude, Codex, ChatGPT, and Cursor with safe LaTeX editing and review. | |
| Random Design yanislav-igonin/random-design-mcp Generate randomized English Markdown frontend design directions from curated catalogs. | |
| WalkMyPlan yaniv-fink/walkmyplan-mcp Describe a house or upload a DWG/vector-PDF plan and get a walkable, editable 3D model. | |
| WP Agent - WordPress publishing & management with Claude yaniv-fink/wp-agent-mcp WordPress MCP server: publish posts, AI images, SEO and full site management, self-hosted | |
| WPWriter — WordPress AI Content & SEO yaniv-fink/wpwriter-mcp WordPress MCP server: generate SEO posts, AI images, autoblog & WooCommerce on your self-hosted site | |
| Somiya yankevych/somiya-mcp Your family's Somiya calendar, tasks and lists. Reads; any change waits for you to confirm. | |
| Base Token Facts yankiifr/base-facts-mcp Base token checks for agents: simulated buy and sell, taxes, honeypots. Pay per call in USDC (x402). | |
| Video Extract yanlinglabs/video-extract-mcp Download any video from a URL, or get its transcript and key frames. All local, no API keys. | |
| Inspectrum yannmenec/inspectrum Review coding-agent plans on demand with peer models, attributed findings, and a structured verdict. | |
| gitpro yantrakar/gitpro Read-only checks of which git name, email and SSH key a repository uses, and why. | |
| io.github.yantrikos/yantrikdb-mcp yantrikos/yantrikdb-mcp Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection | |
| io.github.yaotsakpo/inbin yaotsakpo/inbin-mcp No-signup email for AI agents over MCP: trial inbox, verification codes, parsed email events. | |
| io.github.yaotsakpo/ledgerfc yaotsakpo/ledgerfc-mcp Grounded sports predictions plus European soccer and tennis arbitrage data for AI agents. | |
| Yardstick ATS yardstickinc/yardstick-mcp Manage hiring in Yardstick's ATS: jobs, candidates, applications, interviews, and scorecards. | |
| emperor-folder yarenty/emperor-folder List, read, search and (opt-in) write, edit and move files inside one folder, never outside it. |
19,301–19,350 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.